Veröffentlichungen

@inproceedings{AdaptiveBraincomputerInterfaces2024,

title = {Adaptive Brain-Computer Interfaces Based on Error-Related Potentials and Reinforcement Learning},

author = {Aline Xavier Fidencio and Christian Klaes and Ioannis Iossifidis},

url = {https://abstracts.g-node.org/conference/BC24/abstracts#/uuid/03d3dd16-4c50-43d8-b878-abcfa7857386},

year  = {2024},

date = {2024-09-18},

urldate = {2024-09-24},

booktitle = {BC24 : Computational Neuroscience & Neurotechnology Bernstein Conference 2024},

publisher = {BCCN Bernstein Network Computational Networkvphantom},

abstract = {Error-related potentials (ErrPs) represent the neural signature of error processing in the brain and numerous studies have demonstrated their reliable detection using non-invasive techniques such as electroencephalography (EEG). Over recent decades, the brain-computer interface (BCI) community has shown growing interest in leveraging these intrinsic feedback signals to enhance system performance. However, the effective use of ErrPs in a closed-loop setup crucially depends on accurate single-trial detection, which is typically achieved using a subject-specific classifier (or decoder) trained on samples recorded during extensive calibration sessions before the BCI system can be deployed. In our research, we explore the potential of simulated EEG data for training a truly generic ErrP classifier. Utilizing the SEREEGA simulator, we demonstrate that EEG data can be generated in a cost-effective manner, allowing for controlled and systematic variations in data distribution to accommodate uncertainties in ErrP generation. A classifier trained solely on the generated data exhibits promising generalization capabilities across different datasets and performs comparably to a leave-one-subject-out approach trained on real data (Xavier Fidêncio et al., 2024). In our experiments, we deliberately provoked ErrPs when the BCI misinterpreted the user's intention, resulting in incorrect actions. Subjects engaged in a game controlled via keyboard and/or motor imagery (imagining hand movements), with EEG data recorded using various EEG systems for comparison. Considering the challenges in obtaining clear ErrP signals for all subjects and the limitations identified in existing literature (Xavier Fidêncio et al., 2022), we hypothesize whether a measurable error signal is consistently generated at the scalp level when subjects encounter erroneous conditions, and how this influences closed-loop setups that incorporate ErrPs for improved BCI performance. To address these questions, we assess the effects of the occurrence-to-detection ratio of ErrPs in the classification pipeline using simulated data and explore the impact of error misclassification rates in an ErrP-based learning framework, which employs reinforcement learning to enhance BCI performance.},

keywords = {BCI, Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ControversialOpinionsModel2024,

title = {Controversial Opinions on Model Based and Model Free Reinforcement Learning in the Brain},

author = {Felix Grün and Ioannis Iossifidis},

url = {https://abstracts.g-node.org/conference/BC24/abstracts#/uuid/18e92e07-e4b1-43af-b2ac-ea282f4e81e7},

year  = {2024},

date = {2024-09-18},

urldate = {2024-09-24},

publisher = {BCCN Bernstein Network Computational Networkvphantom},

abstract = {Dopaminergic Reward Prediction Errors (RPEs) are a key motivation and inspiration for model free, temporal difference reinforcement learning methods. Originally, the correlation of RPEs with model free temporal difference errors was seen as a strong indicator for model free reinforcement learning in brains. The standard view was that model free learning is the norm and more computationally expensive model based decision-making is only used when it leads to outcomes that are good enough to justify the additional effort. Nowadays, the landscape of opinions, models and experimental evidence, both electrophysiological and behavioral, paints a more complex picture, including but not limited to mechanisms of arbitration between the two systems. Model based learning or hybrid models better capture experimental behavioral data, and model based signatures are found in RPEs that were previously thought to be model free or hybrid [1]. The evidence for clearly model free learning is scarce [2]. On the other hand, multiple approaches show how model based behavior and RPEs can be produced with fundamentally model free reinforcement learning methods [3, 4, 5]. We point out findings that seem to contradict each other, others that complement each other, speculate which ideas are compatible with each other and give our opinions on ways forward, towards understanding if and how model based and model free learning from rewards coexist and interact in the brain.},

keywords = {Machine Learning, Reinforcement learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{DecodingUpperLimb2024,

title = {Decoding Upper Limb Movements},

author = {Marie Dominique Schmidt and Ioannis Iossifidis},

url = {https://abstracts.g-node.org/conference/BC24/abstracts#/uuid/4725140f-ce7c-4ac5-b694-c627ceeb8d98},

year  = {2024},

date = {2024-09-18},

urldate = {2024-09-24},

publisher = {BCCN Bernstein Network Computational Networkvphantom},

abstract = {The upper limbs are essential for performing everyday tasks that require a wide range of motion and precise coordination. Planning and timing are crucial to achieve coordinated movement. Sensory information about the target and current body state is critical, as is the integration of prior experience represented by prelearned inverse dynamics that generate the associated muscle activity. We propose a generative model that uses a recurrent neural network to predict upper limb muscle activity during various simple and complex everyday movements. By identifying movement primitives within the signal, our model enables the decomposition of these movements into a fundamental set, facilitating the reconstruction of muscle activity patterns. Our approach has implications for the fundamental understanding of movement control and the rehabilitation of neuromuscular disorders with myoelectric prosthetics and functional electrical stimulation.},

keywords = {BCI, Machine Learning, Muscle activity},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{StochasticProcessModel2024,

title = {Stochastic Process Model Derived Indicators of Overfitting for Deep Architectures: Applicability to Small Sample Recalibration of sEMG Decoders},

author = {Stephan Johann Lehmler and Ioannis Iossifidis},

url = {https://abstracts.g-node.org/conference/BC24/abstracts#/uuid/72f03ff1-61dc-443c-92c2-b623d672ce15},

year  = {2024},

date = {2024-09-18},

urldate = {2024-09-24},

booktitle = {BC24 : Computational Neuroscience & Neurotechnology Bernstein Conference 2024},

publisher = {BCCN Bernstein Network Computational Networkvphantom},

abstract = {Our recent work presents a stochastic process model of the activations within an ANN and shows a promising indicator to distinguish memorizing from generalizing ANNs. The average λ, or mean firing rate (MFR), of a hidden layer, shows stable differences between memorizing and generalizing networks, comparatively independent of the underlying data used for evaluation. We first show the performance of this indicator during training on benchmark computer vision datasets such as MNIST and CIFAR-10. In a second step, we extend the work to the real-life use case of calibrating a pre-trained model to a new user. We focus on decoding surface electromyographic (sEMG) signals, which are highly variable within and between users, and therefore necessitate frequent user calibration. Especially in situations when user calibration has to only rely on a small number of samples, degradation in performance overtime due to memorization and overfitting is a not unlikely outcome. In those cases, traditional regularization methods that function by observing the performance on a validation set, such as early stopping, don’t necessarily work, because they are evaluated on data from the same subject and set of movements, which features are being memorized. Our new indicators of memorization could help as stable indicators for model performance and give live insights during model calibration when more samples from the new users would be necessary. We evaluate the usefulness of the MFR-indicator for identifying the moment a pre-trained sEMG decoder starts to memorize given inputs},

keywords = {Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{xavierfidencioExploringErrorrelatedPotentials2023,

title = {Exploring Error-related Potentials in Adaptive Brain-Machine Interfaces: Challenges and Investigation of Occurrence and Detection Ratios},

author = {Aline Xavier Fidencio and Christian Klaes and Ioannis Iossifidis},

year  = {2023},

date = {2023-09-15},

urldate = {2023-09-15},

booktitle = {BC23 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},

publisher = {BCCN Bernstein Network Computational Network},

abstract = {Non-invasive techniques like EEG can record error-related potentials (ErrPs), neural signals associated with error processing and awareness. ErrPs are generated in response to self-made and external errors, including those produced by the BMI. Since ErrPs are implicitly elicited and don’t add extra workload for the subject, they serve as a natural and intrinsic feedback source for developing adaptive BMIs. In our study, we assess the occurrence of interaction ErrPs in an adaptive BMI that combines ErrPs and reinforcement learning. We intentionally provoke ErrPs when the BMI misinterprets the user’s intention and performs an incorrect action. Subjects participated in a game controlled by a keyboard and/or motor imagery (imagining hand movements), and EEG data were recorded using an eight-electrode gel-based EEG system. Results reveal that obtaining a distinct ErrPs signal for each subject is more challenging than anticipated. Current practices report the ErrP in terms of over all subjects and trials difference grand average (error minus correct). This approach has, however, the limitation of masking the inter-trial and subject variability, which are relevant for the online single-trial detection of such signals. Moreover, the reported ErrPs waveshape exhibit differences in terms of components observed, as well as their respective latencies, even when very similar tasks are used. Consequently, we conducted additional individualized data analysis to gain deeper insights into the single-trial nature of the ErrPs. As a result, we determined the need for a better understanding and further investigation of how effectively the ErrPs waveforms generalize across subjects, tasks, experimental protocols, and feedback modalities. Given the challenges in obtaining a clear signal for all subjects and the limitations found in existing literature (Xavier Fidêncio et al., 2022), we hypothesize whether an error signal measurable at the scalp level is consistently generated when subjects encounter erroneous conditions. To address this question, we will assess the occurrence-to-detection ratio of ErrPs using invasive and non-invasive recording techniques, examining how uncertainties regarding error generation in the brain impact the learning pipeline.},

keywords = {BCI, EEG, Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{grunInvestigationInterplayModelBased2023,

title = {Investigation of the Interplay of Model-Based and Model-Free Learning Using Reinforcement Learning},

author = {Felix Grün and Ioannis Iossifidis},

year  = {2023},

date = {2023-09-15},

urldate = {2023-09-15},

booktitle = {BC23 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},

publisher = {BCCN Bernstein Network Computational Network},

abstract = {The reward prediction error hypothesis of dopamine in the brain states that activity of dopaminergic neurons in certain brain regions correlates with the reward prediction error that corresponds to the temporal difference error, often used as a learning signal in model free reinforcement learning (RL). This suggests that some form of reinforcement learning is used in animal and human brains when learning a task. On the other hand, it is clear that humans are capable of building an internal model of a task, or environment, and using it for planning, especially in sequential tasks. In RL, these two learning approaches, model-driven and reward-driven, are known as model based and model-free RL approaches. Both systems were previously thought to exist in parallel, with some higher process choosing which to use. A decade ago, research suggested both could be used concurrently, with some subject-specific weight assigned to each [1]. Still, the prevalent belief appeared to be that model-free learning is the default mechanism used, replaced or assisted by model-based planning only when the task demands it, i.e. higher rewards justify the additional cognitive effort. Recently, Feher da Silva et al. [2] questioned this belief, presenting data and analyses that indicate model-based learning may be used on its own and can even be computationally more efficient. We take a RL perspective, consider different ways to combine model-based and model-free approaches for modeling and for performance, and discuss how to further study this interplay in human behavioral experiments.},

keywords = {Machine Learning, Reinforcement learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{schmidtLinkMuscleActivity2023,

title = {The Link between Muscle Activity and Upper Limb Kinematics},

author = {Marie Dominique Schmidt and Ioannis Iossifidis},

year  = {2023},

date = {2023-09-15},

urldate = {2023-09-15},

booktitle = {BC23 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},

publisher = {BCCN Bernstein Network Computational Network},

abstract = {The upper limbs are crucial in performing daily tasks that require strength, a wide range of motion, and precision. To achieve coordinated motion, planning and timing are critical. Sensory information about the target and the current body state is essential, as well as integrating past experiences, represented by pre-learned inverse dynamics that generate associated muscle activity. We propose a generative model that predicts upper limb muscle activity from a variety of simple and complex everyday motions by means of a recurrent neural network. The model shows promising results, with a good fit for different subjects and abstracts well for new motions. We handle the high inter-subject variation in muscle activity using a transfer learning approach, resulting in a good fit for new subjects. Our approach has implications for fundamental movement control understanding and the rehabilitation of neuromuscular diseases using myoelectric prostheses and functional electrical stimulation. Our model can efficiently predict both muscle activity and motion trajectory, which can assist in developing more effective rehabilitation techniques.},

keywords = {BCI, Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{grunExploringDistributionParameterizations2022,

title = {Exploring Distribution Parameterizations for Distributional Continuous Control},

author = {Felix Grün and Ioannis Iossifidis},

doi = {10.12751/nncn.bc2022.112},

year  = {2022},

date = {2022-09-15},

urldate = {2022-09-15},

booktitle = {BC22 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},

publisher = {BCCN Bernstein Network Computational Network},

keywords = {Machine Learning, Reinforcement learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lehmlerModelingSubjectSpecfic2022,

title = {Modeling Subject Specfic Surface EMG Features by Means of Deep Learning},

author = {Stephan Johann Lehmler and Muhammad Saif-ur-Rehman and Ioannis Iossifidis},

doi = {10.12751/nncn.bc2022.309},

year  = {2022},

date = {2022-09-15},

urldate = {2022-09-15},

booktitle = {BC22 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},

publisher = {BCCN Bernstein Network Computational Network},

keywords = {BCI, Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{schmidtLinkingMuscleActivity2022,

title = {Linking Muscle Activity and Motion Trajectory},

author = {Marie Dominique Schmidt and Ioannis Iossifidis},

doi = {10.12751/nncn.bc2022.191},

year  = {2022},

date = {2022-09-15},

urldate = {2022-09-15},

booktitle = {BC22 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},

publisher = {BCCN Bernstein Network Computational Network},

keywords = {BCI, Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{sziburisDataset3DHand2022,

title = {A Dataset of 3D Hand Transport Trajectories Determined by Inertial Measurements from a Single Sensor},

author = {Tim Sziburis and Susanne Blex and Ioannis Iossifidis},

doi = {10.12751/nncn.bc2022.186},

year  = {2022},

date = {2022-09-15},

urldate = {2022-09-15},

booktitle = {BC22 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},

publisher = {BCCN Bernstein Network Computational Network},

keywords = {BCI, Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{xavierfidencioClosedloopAdaptationBrainmachine2022,

title = {Closed-Loop Adaptation of Brain-Machine Interfaces Using Error-Related Potentials and Reinforcement Learning},

author = {Aline Xavier Fidencio and Christian Klaes and Ioannis Iossifidis},

doi = {10.12751/nncn.bc2022.136},

year  = {2022},

date = {2022-09-15},

urldate = {2022-09-15},

booktitle = {BC22 : Computational Neuroscience & Neurotechnology Bernstein Conference 2022},

publisher = {BCCN Bernstein Network Computational Network},

keywords = {BCI, Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{fidencioErrorrelatedPotentialsDetection2022,

title = {Error-Related Potentials Detection with Dry- and Wet-Electrode EEG},

author = {Aline Xavier Fidencio and Tobias Glasmachers and Ioannis Iossifidis},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {FENS, Forum 2022},

publisher = {FENS, Federation of European Neuroscience Societies},

abstract = {Electroencephalography (EEG) is a non-invasive technique for measuring brain electrical activity from electrodes placed on the scalp surface. Improvements in this technology are particularly relevant because they also boost brain-machine interfaces (BMI) development. Commonly, gel-based electrodes are used since they guarantee a high-quality signal. Alternatively, dry electrodes have been introduced, more suitable for daily use. In this work, we compare conventional dry and wet electrode systems specifically for the detection of error-related potentials (ErrPs). ErrPs are elicited as a reaction to both self-made and external errors. There has been increased interest in the integration of these signals into BMIs to improve their performance since they provide a convenient source of feedback to the system with no extra workload for the subject. These signals can be used, e.g., to correct errors or even for system adaptation. ErrP-based BMIs in the literature have consistently used wet electrodes. Therefore, even though both electrodes types have been compared for other event-related potentials (e.g., P300), it is relevant to know whether the signal quality for the detection of ErrPs is comparable among them. In this work, we implement a simple game to elicit ErrPs and compare the quality of the measured signals. We tested the feasibility of the experimental protocol to elicit ErrP and the measured ErrP displayed a similar waveshape in terms of observed peaks. However, differences exist in both latencies as well as in their amplitude. These variations and other relevant characteristics have to be further verified with more subjects},

keywords = {BCI, EEG, error-related potentials, Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{schmidtMotionIntentionPrediction2022a,

title = {Motion Intention Prediction},

author = {Marie Dominique Schmidt and Tobias Glasmachers and Ioannis Iossifidis},

year  = {2022},

date = {2022-01-01},

urldate = {2022-01-01},

booktitle = {FENS, Forum 2022},

publisher = {FENS, Federation of European Neuroscience Societies},

abstract = {Motion intention prediction is the key to robot-assisted rehabilitation systems. These can rely on various biological signals. One commonly used signal is the muscle activity measured by an electromyogram that occurs between 50-100 milliseconds before the actual movement, allowing a real-world application to assist in time. We show that upper limb motion can be estimated from the corresponding muscle activity. To this end, eight-arm muscles are mapped to the joint angle, velocity, and acceleration of the shoulder, elbow, and wrist. For this purpose, we specifically develop an artificial neural network that estimates complex motions involving multiple upper limb joints. The network model is evaluated concerning its ability to generalize across subjects as well as for new motions. This is achieved through training on multiple subjects and additional transfer learning methods so that the prediction for new subjects is significantly improved. In particular, this is beneficial for a robust real-world application. Furthermore, we investigate the importance of the different parameters such as angle, velocity, and acceleration for simple and complex motions. Predictions for simple motions along with the main components of complex motions achieve excellent accuracy while joints that do not play a dominant role during the motion have comparatively lower accuracy.},

keywords = {BCI, Machine Learning, movement model, muscle signal generator, recurrent neural network},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{grunOffPolicyContinuousControl2021b,

title = {Off-Policy Continuous Control Using Distributional Reinforcement Learning},

author = {Felix Grün and Tobias Glasmachers and Ioannis Iossifidis},

doi = {10.12751/nncn.bc2021.p001},

year  = {2021},

date = {2021-10-01},

urldate = {2021-10-01},

publisher = {Bernstein Conference},

keywords = {Machine Learning, Reinforcement learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lehmlerTransferLearningPatientSpecific2021b,

title = {Transfer-Learning for Patient Specific Model Re-Calibration: Application to sEMG-Classification},

author = {Stephan Johann Lehmler and Muhammad Saif-ur-Rehman and Tobias Glasmachers and Ioannis Iossifidis},

doi = {10.12751/nncn.bc2021.p005},

year  = {2021},

date = {2021-10-01},

urldate = {2021-10-01},

publisher = {Bernstein Conferen},

keywords = {BCI, Computational Complexity, Deep Transfer-Learning, Machine Learning, transfer learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{schmidtArtificiallyGeneratedMuscle2021b,

title = {Artificially Generated Muscle Signals},

author = {Marie Dominique Schmidt and Tobias Glasmachers and Ioannis Iossifidis},

doi = {10.12751/nncn.bc2021.p111},

year  = {2021},

date = {2021-10-01},

urldate = {2021-10-01},

publisher = {Bernstein Conference},

keywords = {BCI, Machine Learning, movement model, muscle signal generator, recurrent neural network},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{xavierfidencioErrorCorrectionIntegration2021b,

title = {Beyond Error Correction: Integration of Error-Related Potentials into Brain-Computer Interfaces for Improved Performance},

author = {Aline Xavier Fidencio and Tobias Glasmachers and Christian Klaes and Ioannis Iossifidis},

doi = {10.12751/nncn.bc2021.p163},

year  = {2021},

date = {2021-10-01},

urldate = {2021-10-01},

publisher = {Bernstein Conference},

keywords = {BCI, error-related potentials, Machine Learning, Reinforcement learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{grunOffPolicyContinuousControl2021,

title = {Off-Policy Continuous Control Using Distributional Reinforcement Learning},

author = {Felix Grün and Tobias Glasmachers and Ioannis Iossifidis},

doi = {10.12751/nncn.bc2021.p001},

year  = {2021},

date = {2021-09-15},

urldate = {2021-09-15},

booktitle = {BC21 : Computational Neuroscience & Neurotechnology Bernstein Conference 2021},

publisher = {BCCN Bernstein Network Computational Network},

keywords = {Machine Learning, Reinforcement learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{lehmlerTransferLearningPatientSpecific2021,

title = {Transfer-Learning for Patient Specific Model Re-Calibration: Application to sEMG-Classification},

author = {Stephan Johann Lehmler and Muhammad Saif-ur-Rehman and Tobias Glasmachers and Ioannis Iossifidis},

doi = {10.12751/nncn.bc2021.p005},

year  = {2021},

date = {2021-09-15},

urldate = {2021-09-15},

booktitle = {BC21 : Computational Neuroscience & Neurotechnology Bernstein Conference 2021},

publisher = {BCCN Bernstein Network Computational Network},

keywords = {BCI, Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{schmidtArtificiallyGeneratedMuscle2021,

title = {Artificially Generated Muscle Signals},

author = {Marie Dominique Schmidt and Tobias Glasmachers and Ioannis Iossifidis},

doi = {10.12751/nncn.bc2021.p111},

year  = {2021},

date = {2021-09-15},

urldate = {2021-09-15},

booktitle = {BC21 : Computational Neuroscience & Neurotechnology Bernstein Conference 2021},

publisher = {BCCN Bernstein Network Computational Network},

keywords = {BCI, Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{sziburisModellingGenerationHuman2021,

title = {Modelling the Generation of Human Upper-Limb Reaching Trajectories: An Extended Behavioural Attractor Dynamics Approach},

author = {Tim Sziburis and Susanne Blex and Tobias Glasmachers and Inaki Rano and Ioannis Iossifidis},

doi = {10.12751/nncn.bc2021.p078},

year  = {2021},

date = {2021-09-15},

urldate = {2021-09-15},

booktitle = {BC21 : Computational Neuroscience & Neurotechnology Bernstein Conference 2021},

publisher = {BCCN Bernstein Network Computational Network},

keywords = {BCI, Machine Learning, movement model},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{fidencioApplicationReinforcementLearning2021,

title = {Application of Reinforcement Learning to a Mining System},

author = {Aline Xavier Fidencio and Tobias Glasmachers and Daniele Naro},

doi = {10.1109/SAMI50585.2021.9378663},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

booktitle = {2021 IEEE 19th World Symposium on Applied Machine Intelligence and Informatics (SAMI)},

pages = {000111--000118},

abstract = {Automation techniques have been widely applied in different industry segments, among others, to increase both productivity and safety. In the mining industry, with the usage of such systems, the operator can be removed from hazardous environments without compromising task execution and it is possible to achieve more efficient and standardized operation. In this work a study case on the application of machine learning algorithms to a mining system example is presented, in which reinforcement learning algorithms were used to solve a control problem. As an example, a machine chain consisting of a Bucket Wheel Excavator, a Belt Wagon and a Hopper Car was used. This system has two material transfer points that need to remain aligned during operation in order to allow continuous material flow. To keep the alignment, the controller makes use of seven degrees of freedom given by slewing, luffing and crawler drives. Experimental tests were done in a simulated environment with two state-of-the-art algorithms, namely Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC). The trained agents were evaluated in terms of episode return and length, as well as alignment quality and action values used. Results show that, for the given task, the PPO agent performs quantitatively and qualitatively better than the SAC agent. However, none of the agents were able to completely solve the proposed testing task.},

keywords = {Control Applications, Industrial Application, Machine Learning, Machine learning algorithms, Mining Industry, Reinforcement learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Hussain2020,

title = {Comparison of Anomaly Detection between Statistical Method and Undercomplete},

author = {Muhammad Ayaz Hussain and Muhammad Saif-ur-Rehman and Christian Klaes and Ioannis Iossifidis},

doi = {https://doi.org/10.1145/3404687.3404689},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

booktitle = {IEEE IInternational Congress on Big Data},

pages = {32--38},

address = {Los Angeles, USA},

keywords = {Anomaly Detection, Autoencoder, Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Hussain2019,

title = {Comparison of Anomaly Detection between Statistical Method and Undercomplete},

author = {Muhammad Ayaz Hussain and Muhammad Saif-ur-Rehman and Christian Klaes and Ioannis Iossifidis},

year  = {2019},

date = {2019-01-01},

urldate = {2019-01-01},

booktitle = {IEEE IInternational Congress on Big Data},

address = {Los Angeles, USA},

keywords = {Anomaly Detection, Autoencoder, Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Noth2012a,

title = {An integrated architecture for the development and assessment of ADAS},

author = {S Noth and Johann Edelbrunner and Ioannis Iossifidis},

doi = {10.1109/ITSC.2012.6338805},

isbn = {9781467330640},

year  = {2012},

date = {2012-01-01},

urldate = {2012-01-01},

booktitle = {IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC},

abstract = {Advanced Driver Assistant Systems act, by definition in natural, often poorly structured, environments and are supposed to closely interact with human operators. Both, natural environments as well as human behaviour have no inherent metric and can not be modelled/measured in the classical way physically plausibly behaving systems are described. textcopyright 2012 IEEE.},

keywords = {ADAS, Autonomous Driving, Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Noth2012b,

title = {A Versatile Simulated Reality Framework: From Embedded Components to ADAS},

author = {Sebastian Noth and Johann Edelbrunner and Ioannis Iossifidis},

year  = {2012},

date = {2012-01-01},

booktitle = {International Conference on Pervasive and Embedded and Communication Systems, 2012, PECCS2012},

keywords = {Autonomous robotics, Machine Learning, simulated reality, Simulation, virtual reality},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Dogan2011a,

title = {Autonomous driving: A comparison of machine learning techniques by means of the prediction of lane change behavior},

author = {Ürün Dogan and Johann Edelbrunner and Ioannis Iossifidis},

doi = {10.1109/ROBIO.2011.6181557},

issn = {01962892},

year  = {2011},

date = {2011-01-01},

booktitle = {2011 IEEE International Conference on Robotics and Biomimetics, ROBIO 2011},

pages = {1837--1843},

abstract = {In the presented work we compare machine learning techniques in the context of lane change behavior performed by humans in a semi-naturalistic simulated environment. We evaluate different learning approaches using differing feature combinations in order to identify appropriate feature, best feature combination, and the most appropriate machine learning technique for the described task. Based on the data acquired from human drivers in the traffic simulator NISYS TRS1, we trained a recurrent neural network, a feed forward neural network and a set of support vector machines. In the followed test drives the system was able to predict lane changes up to 1.5 sec in beforehand.},

keywords = {ADAS, Autonomous Driving, lane change prediction, Machine Learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Dogan2011b,

title = {Autonomous Driving: A Comparison of Machine Learning Techniques by Measns of the Prediction of Lane Change Behavior},

author = {Urun Dogan and Johann Edelbrunner and Ioannis Iossifidis},

year  = {2011},

date = {2011-01-01},

urldate = {2011-01-01},

booktitle = {Proc. IEEE/RSJ International Conference on Robotics and Biomimetics (RoBio2011)},

keywords = {driver information systems, feed forward neural network, lane change maneuvers, Machine Learning, recurrent neural network, support vector machines, traffic simulator},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Noth2011,

title = {Simulated reality environment for development and assessment of cognitive robotic systems},

author = {Sebastian Noth and Ioannis Iossifidis},

year  = {2011},

date = {2011-01-01},

urldate = {2011-01-01},

booktitle = {Proc. IEEE/RSJ International Conference on Robotics and Biomimetics (RoBio2011)},

abstract = {Simulated reality environment incorporating humans and physically plausible behaving robots, providing natural interaction channels, with the option to link simulator to real perception and motion, is gaining importance for the development of cognitive, intuitive interacting and collaborating robotic systems. 

 

 In the present work we introduce a head tracking system which is utilized to incorporate human ego motion in simulated environment improving immersion in the context of human-robot collaborative tasks.},

keywords = {Autonomous robotics, Machine Learning, Simulation, virtual reality},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Dogan2008b,

title = {Towards a Driver Model: Preliminary Study of Lane Change Behavior},

author = {Ueruen Dogan and Hannes Edelbrunner and Ioannis Iossifidis},

url = {http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=4732700},

doi = {10.1109/ITSC.2008.4732700},

isbn = {978-1-4244-2111-4},

year  = {2008},

date = {2008-10-01},

booktitle = {2008 11th International IEEE Conference on Intelligent Transportation Systems},

pages = {931--937},

publisher = {IEEE},

abstract = {The presented work formulates an framework in which early prediction of drivers lane change behavior is realized. We aim to build a representation of drivers lane change behavior in order to recognize and to predict driver's intentions as a first step towards a realistic driver model. In the test bed of the Institute of Neuroinformatik, based on the traffic simulator NISYS TRS 1, 10 individuals have driven in the experiments and they performed more then 150 lane change maneuvers. Lane-offset, distance to the front car and time to contact, were recorded. The acquired data was used to train - in parallel- a recurrent neural network, a feed forward neural network and a set of support vector machines. In the followed test drives the system was able of performing a lane change prediction time of 1.5 sec beforehand. The proposed approach describes a framework for lane-change detection and prediction, which will serve as a prerequisite for a successful driver model.},

keywords = {driver information systems, driver model, drivers lane change behavior prediction, feed forward neural network, feedforward neural nets, lane change maneuvers, Machine Learning, recurrent neural nets, recurrent neural network, support vector machines, traffic simulator},

pubstate = {published},

tppubtype = {inproceedings}

}